74 skills · sorted by relevance
Undo development changes recorded by GSD using Git revert. Select recent commits or target an entire phase or plan, with dependency checks and confirmation before the rollback runs.
Audits Solidity liquidation mechanisms for denial of service vulnerabilities including unbounded loops over positions causing out-of-gas reverts, data structure corruption preventing liquidation, front-running to block liquidation via nonce changes or self-liquidation, pending withdrawals forcing reverts, malicious ERC721/ERC20 callback reverts, collateral in external vaults not seized, insufficient insurance fund blocking liquidation, fixed bonus exceeding available collateral, incorrect decimal handling, conflicting nonReentrant modifiers, zero value transfer reverts, token deny list issues, and single borrower edge cases
The English summary is being prepared. Showing the original description.
Git-aware smart revert for tracks, phases, and tasks. Handles rewritten history, finds related commits, and provides safe rollback with multiple confirmation gates.
The English summary is being prepared. Showing the original description.
Customize cmux keyboard shortcuts for workflows such as tmux-style commands, Vim-style pane movement, or notification handling. It helps inspect existing bindings, apply selected changes, validate supported settings, and provide precise instructions for reverting them.
Audit external compatibility between two DSH (DeepSeek Harness) versions and detect reverts, producing an upgrade-report directory; compares git tags with a source checkout, or published npm packages without one. Use whenever the user asks to check/compare/audit two DSH versions or whether upgrading is safe — e.g. "more changes or reverts in dsh-vX -> dsh-vY", "compare the breaking changes" — even with only two version numbers and no source location. Read-only outside the report directory; npm mode installs in isolation with --ignore-scripts.
The English summary is being prepared. Showing the original description.
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate concession-threshold guard that blocks acceptance on unresolved critical findings. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".
The English summary is being prepared. Showing the original description.
Stops an agent from destroying uncommitted work with git. Requires git status and git diff before any command that discards changes, treats "revert" and "undo" as manual edits, and never runs reset, checkout, clean, stash drop, or force push without explicit approval. Use when a task involves reverting, undoing, resetting, cleaning, rebasing, or force pushing, or before any git command in a repo with uncommitted changes.
The English summary is being prepared. Showing the original description.
[AUTO-INVOKE] MUST be invoked when debugging failed on-chain transactions. Covers transaction receipt analysis, gas diagnosis, calldata decoding, revert reason extraction, and state verification. Trigger: any task involving failed tx analysis, revert debugging, or on-chain transaction troubleshooting.
The English summary is being prepared. Showing the original description.
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".
The English summary is being prepared. Showing the original description.
단일 파일 원위치 revert 로 RED 재검증
The English summary is being prepared. Showing the original description.
Use when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, 'optimize coverage/bundle size/lint count', 'iterate until the metric improves'. NOT for subjective cleanup (see mk:cook), known-root-cause bugs (see mk:fix), behavioral grading (see mk:evaluate), or shipping (see mk:ship).
The English summary is being prepared. Showing the original description.
If CGM fails or is removed, revert the insulin pump to manual mode provided basic criteria for pump use in hospital are still met. Trigger phrase: "CGM failed, should we switch pump to manual mode?
The English summary is being prepared. Showing the original description.
Prefab / Scene / Asset を壊さず編集する。preflight 診断 → dry-run 差分 → confirm + change_reason 監査 → runtime 検証の 4 段ゲートを 1 経路で踏む。 トリガー: パッチ適用、Prefab Variant 編集、`set_property` / `patch_apply` / `revert_overrides` を伴う変更全般。
The English summary is being prepared. Showing the original description.
実験駆動の反復改善ループ（autoresearch 方式）。毎回フレッシュなサブエージェントで 1変更→測定→保持 or revert。progress.md がイテレーション間の記憶。パフォーマンス最適化、リファクタリング、UI改善、バグ修正の試行錯誤に使う。「最適化して」「パフォーマンス改善」「リファクタリング」「試行錯誤して」「実験的に改善」で発動。
The English summary is being prepared. Showing the original description.
Apply one logical code change with mandatory impact mapping, git snapshot, verification, and automatic revert on failure. Load when the user asks for a safe edit, verified change, one change at a time with rollback, or codespine-style edit loop. Also triggers on "safe change", "edit with verification", "don't break the build", "revert if tests fail", or any non-trivial code edit where blast radius matters. Always runs dependency-mapping first. Pairs with incremental-implementation for multi-slice work; this skill is one atomic verify cycle per invocation.
The English summary is being prepared. Showing the original description.
Establish a Git workflow for team development, from choosing branches for separate changes to writing clear commits and pull requests. Includes history cleanup, merge versus rebase decisions, conflict resolution, and release tagging.
Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.
Build GSAP animations in React or Next.js with guidance on useGSAP, element references, and component boundaries. It covers cleanup when components update or disappear, plus keeping animation code out of server rendering.
Guide Git operations with explicit authorization for history changes and destructive actions. It defines recovery snapshots before discarding work, careful handling of locks and index corruption, and checks that keep unexplained changes out of commits.
Integrate GSAP animations into React and Next.js components using useGSAP, element references, and scoped selectors. The skill guides dependency updates, event callbacks, and cleanup when components unmount, while keeping animation code out of server rendering.
Improve code through repeated experiments against a measurable target, such as execution time or memory use. After defining scope and constraints, the agent tests changes, keeps improvements, reverts unsuccessful attempts, and logs results.
Use Stratus Red Team to simulate attack techniques across AWS, Azure, GCP, and Kubernetes. Prepare test resources, run and repeat simulations, check logs and alerts, and remove resources to assess whether security detections work.
Prepare a deployment checklist covering tests, approvals, database changes, release steps, and monitoring. Tailor it to the release and document rollback triggers, the conditions for reverting a change, before production deployment begins.
Improve an existing skill by checking its structure and category requirements, proposing focused fixes, and testing again. Compare failure and warning counts to decide whether to keep changes or restore the previous content.